What is iberant-ai-starter-kit CLAUDE.md?

A CLAUDE.md file is a set of instructions for Claude Code and other coding assistants working in a repository. This one describes a Spanish starter kit containing setup guidance and copyable templates, rather than an application to build.

Use it when maintaining the starter kit, its guide, and templates for agent instructions, setup scripts, commands, hooks, pull requests, and postmortems. Verification means checking the prose, code examples, and links.

It prevents contributors from trying to run builds or tests that do not exist in the kit. It also explains the repository layout and the conventions for editing its documentation.

How iberant/iberant-ai-starter-kit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to iberant/iberant-ai-starter-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/iberant/iberant-ai-starter-kit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/iberant/iberant-ai-starter-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/iberant/iberant-ai-starter-kit/claude-md.svg)](https://agentmods.dev/instructions/iberant/iberant-ai-starter-kit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/iberant/iberant-ai-starter-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/iberant/iberant-ai-starter-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 989 This file is loaded in full into every session.

When invoked 989 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00989	$0.00989
Opus 5	$0.00495	$0.00495
Sonnet 5	$0.00198	$0.00198
Haiku 4.5	$0.00099	$0.00099

Measured 6d ago against content hash c95a1f8c0897, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

iberant-ai-starter-kit CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

This is a starter kit, not an application. It ships two things:

A step-by-step guide (in Spanish) for making any project — greenfield or brownfield — ready to work with AI coding assistants (Claude Code, Codex) productively and safely.
Copy-paste templates under templates/ that users drop into their own project's root (agent instructions, setup scripts, slash commands, hooks, PR template, postmortems).

There is no build, test, or lint here — no package.json, no source code, no CI. The pnpm/dotnet commands you see in the docs and in templates/ are instructions for the downstream project that adopts the kit; they do not run against this repo. Don't try to "run" or "build" this repo. Verification here means: prose is correct, code blocks are valid, and cross-references resolve.

Layout

README.md — entry point and the recurring per-task checklist.
STARTUP.md — the full guide. This is the primary document. Part A = one-time repo setup; Part B = the recurring per-feature/bug cycle (worktree → explore → plan → implement → review → PR → human-review → merge).
WALKTHROUGH.md — a simulated end-to-end session (building a minesweeper) illustrating the Part B flow.
templates/ — the artifacts users copy. Mirrors a target project's root: AGENTS.md, .claude/ (settings, commands, skills), scripts/, docs/, examples/, .github/.

Core conventions (these govern edits here)

Language split is a hard rule. Team-facing docs/guides (README.md, STARTUP.md, WALKTHROUGH.md) are written in Spanish. Everything inside templates/ and any code, commands, filenames, identifiers, and commit messages are English. Keep this split when editing.
AGENTS.md is the source of truth; CLAUDE.md is a symlink to it. In templates/, templates/CLAUDE.md reads as identical to templates/AGENTS.md because it is that symlink — edit templates/AGENTS.md, never the symlink. (This repo's own root CLAUDE.md — this file — is a normal file, not a symlink.)
AGENTS.md must stay under 200 lines. The kit's own thesis is that LLMs reliably follow only ~150–200 instructions; occasional knowledge belongs in skills or docs/ sub-files referenced with @docs/..., not inline. Respect this when editing templates/AGENTS.md.
Code style lives in the linter, not in agent instructions. Don't add style rules to AGENTS.md.

Read the full file on GitHub · 64 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 64 lines · 989 tokens per session scan A c95a1f8c0897

Subscribe to this mod's changes

iberant-ai-starter-kit CLAUDE.md is an instructions file published in the GitHub repository iberant/iberant-ai-starter-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 989 tokens to every session, about $0.0049 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

iberant-ai-starter-kit: Instructions file for Claude Code